CN116245839A - Knee joint cartilage segmentation method, device, equipment and medium - Google Patents
Knee joint cartilage segmentation method, device, equipment and medium Download PDFInfo
- Publication number
- CN116245839A CN116245839A CN202310176233.6A CN202310176233A CN116245839A CN 116245839 A CN116245839 A CN 116245839A CN 202310176233 A CN202310176233 A CN 202310176233A CN 116245839 A CN116245839 A CN 116245839A
- Authority
- CN
- China
- Prior art keywords
- target
- image
- tag
- hard bone
- cartilage
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 210000000845 cartilage Anatomy 0.000 title claims abstract description 95
- 230000011218 segmentation Effects 0.000 title claims abstract description 87
- 238000000034 method Methods 0.000 title claims abstract description 56
- 210000000629 knee joint Anatomy 0.000 title claims abstract description 48
- 210000000988 bone and bone Anatomy 0.000 claims abstract description 103
- 238000012545 processing Methods 0.000 claims abstract description 26
- 238000002591 computed tomography Methods 0.000 claims description 64
- 238000004590 computer program Methods 0.000 claims description 12
- 210000003127 knee Anatomy 0.000 claims description 11
- 238000001228 spectrum Methods 0.000 claims description 6
- PXFBZOLANLWPMH-UHFFFAOYSA-N 16-Epiaffinine Natural products C1C(C2=CC=CC=C2N2)=C2C(=O)CC2C(=CC)CN(C)C1C2CO PXFBZOLANLWPMH-UHFFFAOYSA-N 0.000 claims description 5
- 238000010586 diagram Methods 0.000 description 10
- 230000006870 function Effects 0.000 description 7
- 238000004891 communication Methods 0.000 description 6
- 230000003287 optical effect Effects 0.000 description 5
- 230000004927 fusion Effects 0.000 description 4
- 238000007500 overflow downdraw method Methods 0.000 description 3
- 210000003484 anatomy Anatomy 0.000 description 2
- 210000001264 anterior cruciate ligament Anatomy 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 238000007499 fusion processing Methods 0.000 description 2
- 239000013307 optical fiber Substances 0.000 description 2
- 230000000644 propagated effect Effects 0.000 description 2
- 239000004065 semiconductor Substances 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000007797 corrosion Effects 0.000 description 1
- 238000005260 corrosion Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000003628 erosive effect Effects 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 238000003709 image segmentation Methods 0.000 description 1
- 230000003902 lesion Effects 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 230000000877 morphologic effect Effects 0.000 description 1
- PTLRDCMBXHILCL-UHFFFAOYSA-M sodium arsenite Chemical compound [Na+].[O-][As]=O PTLRDCMBXHILCL-UHFFFAOYSA-M 0.000 description 1
- 210000004872 soft tissue Anatomy 0.000 description 1
- 238000001356 surgical procedure Methods 0.000 description 1
- 210000002303 tibia Anatomy 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
- 210000000689 upper leg Anatomy 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0012—Biomedical image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T3/00—Geometric image transformations in the plane of the image
- G06T3/14—Transformations for image registration, e.g. adjusting or mapping for alignment of images
- G06T3/147—Transformations for image registration, e.g. adjusting or mapping for alignment of images using affine transformations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
- G06V10/761—Proximity, similarity or dissimilarity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10072—Tomographic images
- G06T2207/10081—Computed x-ray tomography [CT]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10072—Tomographic images
- G06T2207/10088—Magnetic resonance imaging [MRI]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20021—Dividing image into blocks, subimages or windows
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20092—Interactive image processing based on input by user
- G06T2207/20104—Interactive definition of region of interest [ROI]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30004—Biomedical image processing
- G06T2207/30008—Bone
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Health & Medical Sciences (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Quality & Reliability (AREA)
- Radiology & Medical Imaging (AREA)
- Artificial Intelligence (AREA)
- Computing Systems (AREA)
- Databases & Information Systems (AREA)
- Evolutionary Computation (AREA)
- Software Systems (AREA)
- Multimedia (AREA)
- Apparatus For Radiation Diagnosis (AREA)
Abstract
The embodiment of the disclosure relates to a knee joint cartilage segmentation method, a device, equipment and a medium, wherein the method comprises the following steps: acquiring a target MR image and a corresponding target CT image of a knee joint of a user; the target CT image is provided with a corresponding first hard bone tag, a second hard bone tag of the target MR image is determined based on the first hard bone tag, a target deformation field between the target CT image and the target MR image, a target map matched with the target MR image is obtained from a plurality of candidate maps in a preset map library, a segmentation interested region of the target MR image is determined based on the second hard bone tag and cartilage tags of the target map for processing, a plurality of template image blocks are obtained in the segmentation interested region, and a tag value of the target MR image is determined according to a tag value of each template image block, so that a segmentation result of the target MR image is obtained. By adopting the technical scheme, the cartilage distribution position is determined through the hard bones of the knee joint, so that the cartilage segmentation precision is improved.
Description
Technical Field
The disclosure relates to the technical field of intelligent medical surgery, in particular to a knee joint cartilage segmentation method, device, equipment and medium.
Background
In a knee anterior cruciate ligament (Anterior Cruciate Ligament, ACL) reconstruction surgical robot, accurate segmentation of cartilage and reconstruction of cartilage surface are the basis for realizing accurate positioning of the surgical robot; the observation of cartilage morphology can also provide an important basis for the diagnosis of cartilage lesions, whereas cartilage segmentation is the first step in the observation of cartilage morphology. Since MR (Magnetic Resonance) images have a relatively high contrast with respect to cartilage and soft tissue, it is common in clinic to observe cartilage using MR images.
At present, cartilage segmentation is performed on a target MR image by a manual mode, so that the time is long and the accuracy is low.
Disclosure of Invention
In order to solve or at least partially solve the above technical problems, the present disclosure provides a knee joint cartilage segmentation method, device, apparatus and medium.
Embodiments of the present disclosure provide a knee joint cartilage segmentation method, the method comprising:
acquiring a target Magnetic Resonance (MR) image of a knee joint of a user and a corresponding target Computed Tomography (CT) image; wherein, the target CT image has a corresponding first hard bone tag;
determining a second hard bone tag of the target MR image based on the first hard bone tag, a target deformation field between the target CT image and the target MR image;
acquiring target maps matched with the target MR image from a plurality of candidate maps in a preset map library;
processing based on the second hard bone tag and a cartilage tag of the target atlas to determine a segmented region of interest of the target MR image;
and acquiring a plurality of template image blocks in the segmented region of interest, and determining the tag value of the target MR image according to the tag value of each template image block to obtain a segmentation result of the target MR image.
Embodiments of the present disclosure also provide a knee joint cartilage segmentation device, the device comprising:
the first acquisition module is used for acquiring a target magnetic resonance MR image of the knee joint of the user and a corresponding target computed tomography CT image; wherein, the target CT image has a corresponding first hard bone tag;
a first determination module for determining a second hard bone tag of the target MR image based on a target deformation field between the first hard bone tag, the target CT image, and the target MR image;
the second acquisition module is used for acquiring target spectrums matched with the target MR image from a plurality of candidate spectrums in a preset spectrum library;
a second determining module for determining a segmented region of interest of the target MR image based on processing the second hard bone tag and a cartilage tag of the target atlas;
a third acquisition module, configured to acquire a plurality of template image blocks in the segmented region of interest;
and the third determining module is used for determining the label value of the target MR image according to the label value of each template image block to obtain the segmentation result of the target MR image.
The embodiment of the disclosure also provides an electronic device, which comprises: a processor; a memory for storing the processor-executable instructions; the processor is configured to read the executable instructions from the memory and execute the instructions to implement a knee cartilage segmentation method according to an embodiment of the present disclosure.
The present disclosure also provides a computer-readable storage medium storing a computer program for executing the knee joint cartilage segmentation method as provided by the embodiments of the present disclosure.
Compared with the prior art, the technical scheme provided by the embodiment of the disclosure has the following advantages: according to the knee joint cartilage segmentation scheme provided by the embodiment of the disclosure, a target MR image and a corresponding target CT image of a knee joint of a user are acquired; the target CT image is provided with a corresponding first hard bone tag, a second hard bone tag of the target MR image is determined based on the first hard bone tag, a target deformation field between the target CT image and the target MR image, a target map matched with the target MR image is obtained from a plurality of candidate maps in a preset map library, a segmentation interested region of the target MR image is determined based on the second hard bone tag and a cartilage tag of the target map for processing, a plurality of template image blocks are obtained in the segmentation interested region, and a tag value of the target MR image is determined according to a tag value of each template image block, so that a segmentation result of the target MR image is obtained. By adopting the technical scheme, the cartilage distribution position is determined through the hard bones of the knee joint, so that the cartilage segmentation precision is improved.
Drawings
The above and other features, advantages, and aspects of embodiments of the present disclosure will become more apparent by reference to the following detailed description when taken in conjunction with the accompanying drawings. The same or similar reference numbers will be used throughout the drawings to refer to the same or like elements. It should be understood that the figures are schematic and that elements and components are not necessarily drawn to scale.
Fig. 1 is a schematic flow chart of a knee joint cartilage segmentation method according to an embodiment of the present disclosure;
fig. 2 is a flow chart of another knee cartilage segmentation method according to an embodiment of the present disclosure;
FIG. 3 is a flow chart of a target MR image hard bone segmentation provided in an embodiment of the disclosure;
FIG. 4 is a schematic illustration of a pattern selection provided in an embodiment of the present disclosure;
FIG. 5 is a schematic diagram of acquiring a segmented ROI region of a target MR image according to an embodiment of the present disclosure;
fig. 6 is a schematic diagram of an image block template library establishment provided in an embodiment of the present disclosure;
fig. 7 is a schematic structural view of a knee joint cartilage dividing device according to an embodiment of the present disclosure;
fig. 8 is a schematic structural diagram of an electronic device according to an embodiment of the disclosure.
Detailed Description
Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While certain embodiments of the present disclosure have been shown in the accompanying drawings, it is to be understood that the present disclosure may be embodied in various forms and should not be construed as limited to the embodiments set forth herein, but are provided to provide a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are for illustration purposes only and are not intended to limit the scope of the present disclosure.
It should be understood that the various steps recited in the method embodiments of the present disclosure may be performed in a different order and/or performed in parallel. Furthermore, method embodiments may include additional steps and/or omit performing the illustrated steps. The scope of the present disclosure is not limited in this respect.
The term "including" and variations thereof as used herein are intended to be open-ended, i.e., including, but not limited to. The term "based on" is based at least in part on. The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments. Related definitions of other terms will be given in the description below.
It should be noted that the terms "first," "second," and the like in this disclosure are merely used to distinguish between different devices, modules, or units and are not used to define an order or interdependence of functions performed by the devices, modules, or units.
It should be noted that references to "one", "a plurality" and "a plurality" in this disclosure are intended to be illustrative rather than limiting, and those of ordinary skill in the art will appreciate that "one or more" is intended to be understood as "one or more" unless the context clearly indicates otherwise.
The names of messages or information interacted between the various devices in the embodiments of the present disclosure are for illustrative purposes only and are not intended to limit the scope of such messages or information.
In general, a segmentation method based on multiple atlases maps labels in an atlas library onto a target image through registration, and obtains a final segmentation result of the target image through label fusion. Registration is an important step in a multi-map segmentation method, has an important influence on segmentation accuracy, but when the shape difference between a map image and a target image is large, registration accuracy is reduced, and the map image cannot be spatially aligned with the target image, so that label fusion accuracy is affected.
Specifically, the knee joint cartilage is attached to the surface of the hard bone on an anatomical structure, the CT (Computed Tomography ) image is clear in development of the hard bone, the hard bone morphology can be observed by utilizing the target CT image, and the hard bone segmentation precision of the target CT image is high compared with that of the MR image. Therefore, the knee joint cartilage segmentation method of the embodiment of the disclosure determines cartilage distribution positions through the knee joint hard bones, reduces the influence of poor segmentation precision caused by poor registration precision of the multi-map segmentation method, and improves cartilage segmentation precision.
Fig. 1 is a flow chart of a knee cartilage segmentation method according to an embodiment of the present disclosure, which may be performed by a knee cartilage segmentation device, wherein the device may be implemented in software and/or hardware, and may be generally integrated in an electronic device. As shown in fig. 1, the method includes:
Specifically, the first hard bone tag of the target CT image assists in knee joint cartilage segmentation, and cartilage distribution positions are determined through the hard bones of the knee joint, so that a cartilage segmentation region of interest is determined, and knee joint cartilage segmentation accuracy is improved.
Wherein the target MR image and the target CT image are obtained by photographing the knee joint of the same user.
In the embodiment of the disclosure, after the target CT image is acquired, the target CT image is subjected to hard bone segmentation processing, and the acquired target CT image has a corresponding first hard bone tag, for example, the target CT image is subjected to hard bone segmentation processing by a thresholding method, a graph cutting method, and the like, so as to obtain the first hard bone tag of the target CT image.
The deformation field of the target refers to the deformation field of the target CT image and the target MR image in image registration, and the deformation relationship between the target CT image and the target MR image can be represented through the target deformation field.
In the embodiment of the disclosure, there are various ways of determining the second hard bone tag of the target MR image based on the first hard bone tag, the target deformation field between the target CT image and the target MR image, in some embodiments, the target CT image and the target MR image are rigidly registered to obtain the target deformation field, and the first hard bone tag is deformed by using the target deformation field in a manner of interpolation or the like to obtain the deformed tag image, that is, the second hard bone tag of the target MR image.
And step 103, acquiring a target map matched with the target MR image from a plurality of candidate maps in a preset map library.
In an embodiment of the present disclosure, an atlas library including a plurality of candidate atlas is preset, wherein each candidate atlas is composed of a target MR image and a corresponding label image. The label image contains a cartilage label and a hard bone label. Wherein the hard bone tag is used for subsequent acquisition of template image blocks more similar to the target MR image.
In the embodiment of the disclosure, there are various ways of acquiring a target atlas matching with a target MR image from a plurality of candidate atlas in a preset atlas library, for example, calculating a similarity between each candidate atlas and the target MR image, and determining one or more target atlas from the plurality of candidate atlas according to the similarity and a preset similarity threshold. Wherein the number of target patterns is less than or equal to the number of candidate patterns.
Specifically, there are various ways of determining the segmented region of interest of the target MR image based on processing the second hard bone tag and the cartilage tag of the target map, such as performing a merging operation on the second hard bone tag after performing related processing such as erosion on the second hard bone tag, and performing related processing such as merging on the cartilage tags of all the target maps, to obtain the segmented region of interest.
It will be appreciated that label fusion may be performed on an image block basis, and therefore it is necessary to extract image blocks from the target atlas, obtain a plurality of template image blocks, and in particular extract template image blocks near cartilage using hard bone label prior information on the target atlas, to obtain a plurality of template image blocks more similar to the target MR image.
In the embodiment of the present disclosure, there are various ways of acquiring a plurality of template image blocks in a segmented region of interest, such as determining a target coordinate point (a point closest to a target atlas hard bone tag) in the segmented region of interest from a coordinate point of a target MR image and determining a template image block within a preset region range of the target coordinate point, so that a plurality of template image blocks can be acquired.
In the embodiment of the disclosure, after a plurality of template image blocks are acquired, a plurality of template image blocks are utilized to acquire tag values of a target MR image, such as a majority vote, a weighted vote, and the like, so as to obtain a segmentation result.
According to the knee joint cartilage segmentation scheme provided by the embodiment of the disclosure, a magnetic resonance target MR image of a knee joint of a user and a corresponding computed tomography target CT image are acquired; the target CT image is provided with a corresponding first hard bone tag, a second hard bone tag of the target MR image is determined based on the first hard bone tag, a target deformation field between the target CT image and the target MR image, a target map matched with the target MR image is obtained from a plurality of candidate maps in a preset map library, a segmentation interested region of the target MR image is determined based on the second hard bone tag and a cartilage tag of the target map for processing, a plurality of template image blocks are obtained in the segmentation interested region, and a tag value of the target MR image is determined according to a tag value of each template image block, so that a segmentation result of the target MR image is obtained. By adopting the technical scheme, the cartilage distribution position is determined through the hard bones of the knee joint, so that the cartilage segmentation precision is improved.
Fig. 2 is a flow chart of another knee joint cartilage segmentation method according to an embodiment of the present disclosure, where the knee joint cartilage segmentation method is further optimized based on the above embodiment. As shown in fig. 2, the method includes:
And 202, carrying out rigid registration based on the target CT image and the target MR image, determining a target deformation field, and calculating based on the target deformation field and the first hard bone tag to obtain a second hard bone tag.
Let the target MR image be I MR ={I MR (x) I x epsilon omega, and the corresponding target CT image is I CT ={I CT (x) X ε Ω }, where x represents a voxel, Ω ε R 3 Representing a lattice on the image. It should be noted that, here, the target CT image I CT MR image of a target I MR The knee joint of the same user needs to be photographed. The segmentation target is to respectively assign different label values to the femur cartilage and the tibia cartilage on the target MR image, namely, obtain L MR-cartilage 。
Specifically, the target MR image I MR Is achieved by means of registration. For example, as shown in fig. 3: first of all for I CT Hard bone segmentation is carried out to obtain the correspondingLabel L of (2) CT The segmentation method may be a thresholding method, a graph cut method, or the like. Then CT image I of the object CT MR image of a target I MR Performing rigid registration to obtain deformation field D, and using deformation field D to make label image L CT Deforming to obtain deformed tag image, namely hard bone tag L of target MR image MR-bone 。
And 204, acquiring target atlas from all the to-be-processed atlas according to the similarity of each to-be-processed atlas and the target MR image.
Specifically, it is assumed that there are N candidate maps { a n N=1, 2,..n }, wherein, each candidate atlas is represented by MR atlas image I n Corresponding label image L n Composition is prepared. The label image contains not only cartilage labels but also hard bone labels. Wherein the hard bone tag is used to find template image blocks more similar to the target MR image when the template image block library is built.
For example, the specific acquisition process of the target map is shown in fig. 4; first, each candidate pattern A in the pattern library n MR image of a target I MR Carrying out affine registration, and deforming the affine registration by using a deformation field to obtain a deformed map A to be processed dn The method comprises the steps of carrying out a first treatment on the surface of the Then, respectively combining each deformed map to be processed with the target MR image I MR Similarity calculation and comparison are carried out, and the similarity calculation and comparison are carried out, and I is selected from the deformed map to be processed MR The M most similar target maps form a selected map library { A } dm M=1, 2, M, where M<=n. Thus, choosing the most similar atlas image helps to improve the accuracy of subsequent segmentation.
And 205, performing operation processing on the second hard bone tag to obtain a hard bone tag to be processed, and differentiating the hard bone tag to be processed to obtain a target hard bone tag.
And 206, performing merging operation on the cartilage labels of each target map to obtain a label set, performing closing operation on the label set to obtain target cartilage labels, and performing merging operation on the target cartilage labels to obtain the segmented region of interest.
Specifically, in general, after obtaining a map image library, a multi-map-based segmentation method performs image segmentation by using a label fusion method, and segments a region of interest (ROI, region Of Interest) into regions obtained by combining all map labels. However, when the morphological difference between the map image and the target image is large, the registration process cannot perfectly align the map image and the target image in the space position, so that the obtained ROI area is large, and the difficulty is brought to the subsequent label fusion process. Since cartilage is attached to the surface of a hard bone on an anatomical structure, the embodiment of the disclosure can acquire the distribution position of the cartilage by introducing a hard bone label prior, lock the segmented ROI area on the target image, reduce the segmentation range and improve the segmentation precision.
For example, as shown in FIG. 5, first, the hard bone tag L of the target MR image is displayed MR-bone Respectively performing corrosion operation and expansion operation, and differentiating the obtained label to obtain L MR-edge The method comprises the steps of carrying out a first treatment on the surface of the Then the label L corresponding to each target map in the map library m Performing union operation to obtain union sets of all labels, closing the union sets, filling holes in the union sets to obtain L cartilage-union The method comprises the steps of carrying out a first treatment on the surface of the Finally, L is MR-edge And L is equal to cartilage-union And carrying out merging operation to obtain a final segmented ROI area.
Thus, compared with L obtained by directly obtaining all map labels cartilage-union The final segmented ROI region is more capable of representing cartilage distribution locations, closer to the true cartilage shape.
And step 207, determining a target coordinate point in the segmentation interest region, and determining a template image block in a preset region range of the target coordinate point.
Specifically, the label fusion method is an image block-based label fusion method, so that template image blocks need to be extracted from the map library images to form an image block template library. Assume that on the target MR image, the voxel to be given the label value is p 0 Its coordinate position in the target MR image is (i, j, k), its position in the atlas A m The corresponding voxel in (a) is p 1 . The steps for creating the image block template library are generally as follows: and (3) taking (i, j, k) as a center, extracting image blocks with the sizes of (R, S, T) in a square area with the search space of (W, H, C), and forming a template library with W, H and C image blocks.
However, when the morphology difference between the target atlas and the target MR image is large, the registration process cannot perfectly align the target atlas and the target MR image in space. Therefore, the difference between the image block and the target MR image is large, and the template image block similar to the target MR image cannot be found in the template library. When the image block template library is established, the image block is extracted nearby the cartilage by using the prior information of the hard bone tag on the target map, so that the image block template library which is more similar to the target image block is obtained.
For example, as shown in FIG. 6, the points corresponding to the coordinates (i, j, k) of the target MR image and the target map are p 0 Point and p 1 The point is first on the target MR image, at p 0 Extracting a target image block T with the size of (R, S, T) by taking a point as a center; then searching p on the target map 1 Point p closest to the target atlas hard bone tag 2 In p 2 And (3) taking the point as the center, and extracting template image blocks with the sizes of (R, S and T) in a square area with the search space of (W, H and C). Each target map can extract W.times.H.times.C template image blocks T 1 To T K The M target atlas can extract M.W.H.C template image blocks altogether; dividing M.W.H.C template image blocksRespectively comparing the template image blocks with the target image blocks T in a similarity manner to obtain Q most similar template image blocks T 1 To T Q And forming a final image block template library.
Therefore, the foreground region and the background region of the target MR image can be acquired by acquiring the label value of the target MR image, so that the segmentation result of the target MR image is obtained.
Specifically, the purpose of the label fusion process is to obtain the label of the current target image block by using the template image block in the image block template library according to a certain criterion. There are many methods of tag fusion, most commonly majority voting, weighted voting, etc. The weighted voting method assigns the label value with the largest occurrence number to the current target image block by counting the label value corresponding to the template image block in the image block template library. And the weighted voting gives different weights to each template label according to the similarity of the template image block and the target image block, so that the label value of the target image is obtained. In the weighted voting method, the higher the similarity is, the greater the weight of the label value corresponding to the template image block is.
Therefore, the hard bone prior information of the target CT image and the cartilage prior information of the target MR image are combined to obtain the cartilage distribution prior information of the target MR image, so that the hard bone tag prior of the target MR image is led into the multi-atlas segmentation flow to help determine the cartilage distribution position, thereby determining the cartilage segmentation interested region and finally improving the knee joint cartilage segmentation precision.
Fig. 7 is a schematic structural diagram of a knee cartilage dividing device according to an embodiment of the present disclosure, which may be implemented by software and/or hardware, and may be generally integrated in an electronic device. As shown in fig. 7, the apparatus includes:
a first acquisition module 301, configured to acquire a target magnetic resonance MR image and a corresponding target computed tomography CT image of a knee joint of a user; wherein, the target CT image has a corresponding first hard bone tag;
a first determining module 302 for determining a second hard bone tag of the target MR image based on a target deformation field between the first hard bone tag, the target CT image and the target MR image;
a second obtaining module 303, configured to obtain a target atlas matched with the target MR image from a plurality of candidate atlas in a preset atlas library;
a second determining module 304 for determining a segmented region of interest of the target MR image based on processing the second hard bone label and a cartilage label of the target atlas;
a third obtaining module 305, configured to obtain a plurality of template image blocks in the segmented region of interest;
and a third determining module 306, configured to determine a tag value of the target MR image according to the tag value of each template image block, so as to obtain a segmentation result of the target MR image.
Optionally, the first determining module 302 is specifically configured to:
performing rigid registration based on the target CT image and the target MR image to determine the target deformation field;
and calculating based on the target deformation field and the first hard bone tag to obtain the second hard bone tag.
Optionally, the second obtaining module 303 is specifically configured to:
carrying out affine registration on each candidate map and the target MR image to obtain a deformation field between each candidate map and the target MR image;
processing the label image of each candidate map based on the deformation field between each candidate map and the target MR image to obtain a map to be processed;
and acquiring the target atlas from all the to-be-processed atlas according to the similarity of each to-be-processed atlas and the target MR image.
Optionally, the second determining module 304 is specifically configured to:
processing the second hard bone tag to obtain a hard bone tag to be processed;
differentiating the hard bone label to be processed to obtain a target hard bone label;
combining the cartilage labels of each target atlas to obtain a label set, and performing closing operation on the label set to obtain a target cartilage label;
and carrying out merging operation based on the target hard bone tag and the target cartilage tag to obtain the segmented region of interest.
Optionally, the third obtaining module 305 is specifically configured to:
and determining a target coordinate point in the segmented region of interest, and determining a template image block in a preset region range of the target coordinate point.
Optionally, the third determining module 306 is specifically configured to:
calculating the target similarity of each template image block and a target MR image block in the target MR image;
determining the weight of each template image block according to the target similarity;
and calculating according to the weight of each template image block and the label value of each template image block to obtain the label value of the target MR image, and obtaining the segmentation result of the target MR image.
The knee joint cartilage segmentation device provided by the embodiment of the disclosure can execute the knee joint cartilage segmentation method provided by any embodiment of the disclosure, and has the corresponding functional modules and beneficial effects of the execution method.
Embodiments of the present disclosure also provide a computer program product comprising a computer program/instructions which, when executed by a processor, implement the knee joint cartilage segmentation method provided by any of the embodiments of the present disclosure.
Fig. 8 is a schematic structural diagram of an electronic device according to an embodiment of the disclosure. Referring now in particular to fig. 8, a schematic diagram of an electronic device 400 suitable for use in implementing embodiments of the present disclosure is shown. The electronic device 400 in the embodiments of the present disclosure may include, but is not limited to, mobile terminals such as mobile phones, notebook computers, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), in-vehicle terminals (e.g., in-vehicle navigation terminals), and the like, and stationary terminals such as digital TVs, desktop computers, and the like. The electronic device shown in fig. 8 is merely an example and should not be construed to limit the functionality and scope of use of the disclosed embodiments.
As shown in fig. 8, the electronic device 400 may include a processing means (e.g., a central processing unit, a graphics processor, etc.) 401, which may perform various appropriate actions and processes according to a program stored in a Read Only Memory (ROM) 402 or a program loaded from a storage means 408 into a Random Access Memory (RAM) 403. In the RAM403, various programs and data necessary for the operation of the electronic device 400 are also stored. The processing device 401, the ROM 402, and the RAM403 are connected to each other by a bus 404. An input/output (I/O) interface 405 is also connected to bus 404.
In general, the following devices may be connected to the I/O interface 405: input devices 406 including, for example, a touch screen, touchpad, keyboard, mouse, camera, microphone, accelerometer, gyroscope, etc.; an output device 407 including, for example, a Liquid Crystal Display (LCD), a speaker, a vibrator, and the like; storage 408 including, for example, magnetic tape, hard disk, etc.; and a communication device 409. The communication means 409 may allow the electronic device 400 to communicate with other devices wirelessly or by wire to exchange data. While fig. 8 shows an electronic device 400 having various means, it is to be understood that not all of the illustrated means are required to be implemented or provided. More or fewer devices may be implemented or provided instead.
In particular, according to embodiments of the present disclosure, the processes described above with reference to flowcharts may be implemented as computer software programs. For example, embodiments of the present disclosure include a computer program product comprising a computer program embodied on a non-transitory computer readable medium, the computer program comprising program code for performing the method shown in the flow chart. In such an embodiment, the computer program may be downloaded and installed from a network via communications device 409, or from storage 408, or from ROM 402. When executed by the processing device 401, the computer program performs the above-described functions defined in the knee joint cartilage segmentation method of the embodiment of the present disclosure.
It should be noted that the computer readable medium described in the present disclosure may be a computer readable signal medium or a computer readable storage medium, or any combination of the two. The computer readable storage medium can be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or a combination of any of the foregoing. More specific examples of the computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the context of this disclosure, a computer-readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. In the present disclosure, however, the computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, with the computer-readable program code embodied therein. Such a propagated data signal may take any of a variety of forms, including, but not limited to, electro-magnetic, optical, or any suitable combination of the foregoing. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: electrical wires, fiber optic cables, RF (radio frequency), and the like, or any suitable combination of the foregoing.
In some implementations, the clients, servers may communicate using any currently known or future developed network protocol, such as HTTP (Hyper Text Transfer Protocol ), and may be interconnected with any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network ("LAN"), a wide area network ("WAN"), the internet (e.g., the internet), and peer-to-peer networks (e.g., ad hoc peer-to-peer networks), as well as any currently known or future developed networks.
The computer readable medium may be contained in the electronic device; or may exist alone without being incorporated into the electronic device.
The computer readable medium carries one or more programs which, when executed by the electronic device, cause the electronic device to: acquiring a magnetic resonance target MR image of a knee joint of a user and a corresponding computed tomography target MR image; the target MR image is provided with a corresponding first hard bone tag, a second hard bone tag of the target MR image is determined based on the first hard bone tag, a target MR image and a target deformation field between the target MR image, a target map matched with the target MR image is obtained from a plurality of candidate maps in a preset map library, a segmentation interested region of the target MR image is determined based on the second hard bone tag and a cartilage tag of the target map for processing, a plurality of template image blocks are obtained in the segmentation interested region, and a tag value of the target MR image is determined according to a tag value of each template image block, so that a segmentation result of the target MR image is obtained.
Computer program code for carrying out operations of the present disclosure may be written in one or more programming languages, including, but not limited to, an object oriented programming language such as Java, smalltalk, C ++ and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any kind of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or may be connected to an external computer (for example, through the Internet using an Internet service provider).
The flowcharts and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
The units involved in the embodiments of the present disclosure may be implemented by means of software, or may be implemented by means of hardware. Wherein the names of the units do not constitute a limitation of the units themselves in some cases.
The functions described above herein may be performed, at least in part, by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that may be used include: a Field Programmable Gate Array (FPGA), an Application Specific Integrated Circuit (ASIC), an Application Specific Standard Product (ASSP), a system on a chip (SOC), a Complex Programmable Logic Device (CPLD), and the like.
In the context of this disclosure, a machine-readable medium may be a tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. The machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
According to one or more embodiments of the present disclosure, the present disclosure provides an electronic device comprising:
a processor;
a memory for storing the processor-executable instructions;
the processor is configured to read the executable instructions from the memory and execute the instructions to implement any of the knee cartilage segmentation methods provided in the present disclosure.
According to one or more embodiments of the present disclosure, the present disclosure provides a computer-readable storage medium storing a computer program for performing any one of the knee joint cartilage segmentation methods provided by the present disclosure.
The foregoing description is only of the preferred embodiments of the present disclosure and description of the principles of the technology being employed. It will be appreciated by persons skilled in the art that the scope of the disclosure referred to in this disclosure is not limited to the specific combinations of features described above, but also covers other embodiments which may be formed by any combination of features described above or equivalents thereof without departing from the spirit of the disclosure. Such as those described above, are mutually substituted with the technical features having similar functions disclosed in the present disclosure (but not limited thereto).
Moreover, although operations are depicted in a particular order, this should not be understood as requiring that such operations be performed in the particular order shown or in sequential order. In certain circumstances, multitasking and parallel processing may be advantageous. Likewise, while several specific implementation details are included in the above discussion, these should not be construed as limiting the scope of the present disclosure. Certain features that are described in the context of separate embodiments can also be implemented in combination in a single embodiment. Conversely, various features that are described in the context of a single embodiment can also be implemented in multiple embodiments separately or in any suitable subcombination.
Although the subject matter has been described in language specific to structural features and/or methodological acts, it is to be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or acts described above. Rather, the specific features and acts described above are example forms of implementing the claims.
Claims (10)
1. A method for dividing knee joint cartilage, comprising:
acquiring a target Magnetic Resonance (MR) image of a knee joint of a user and a corresponding target Computed Tomography (CT) image; wherein, the target CT image has a corresponding first hard bone tag;
determining a second hard bone tag of the target MR image based on the first hard bone tag, a target deformation field between the target CT image and the target MR image;
acquiring target maps matched with the target MR image from a plurality of candidate maps in a preset map library;
processing based on the second hard bone tag and a cartilage tag of the target atlas to determine a segmented region of interest of the target MR image;
and acquiring a plurality of template image blocks in the segmented region of interest, and determining the tag value of the target MR image according to the tag value of each template image block to obtain a segmentation result of the target MR image.
2. The knee cartilage segmentation method of claim 1 wherein the determining a second hard bone tag of the target MR image based on a target deformation field between the first hard bone tag, the target CT image and the target MR image comprises:
performing rigid registration based on the target CT image and the target MR image to determine the target deformation field;
and calculating based on the target deformation field and the first hard bone tag to obtain the second hard bone tag.
3. The knee joint cartilage segmentation method according to claim 1, wherein the acquiring a target atlas matching the target MR image from a plurality of candidate atlas in a preset atlas library comprises:
carrying out affine registration on each candidate map and the target MR image to obtain a deformation field between each candidate map and the target MR image;
processing the label image of each candidate map based on the deformation field between each candidate map and the target MR image to obtain a map to be processed;
and acquiring the target atlas from all the to-be-processed atlas according to the similarity of each to-be-processed atlas and the target MR image.
4. The knee cartilage segmentation method of claim 1 wherein the processing based on the second hard bone tag and the cartilage tag of the target atlas to determine the segmented region of interest of the target MR image comprises:
operating the second hard bone tag to obtain a hard bone tag to be processed;
differentiating the hard bone label to be processed to obtain a target hard bone label;
combining the cartilage labels of each target atlas to obtain a label set, and performing closing operation on the label set to obtain a target cartilage label;
and carrying out merging operation based on the target hard bone tag and the target cartilage tag to obtain the segmented region of interest.
5. The knee joint cartilage segmentation method of claim 1 wherein the acquiring a plurality of template image blocks in the segmented region of interest comprises:
and determining a target coordinate point in the segmented region of interest, and determining a template image block in a preset region range of the target coordinate point.
6. The knee cartilage segmentation method of claim 1 wherein the determining the tag value of the target MR image from the tag value of each of the template image blocks results in a segmentation result of the target MR image, comprising:
calculating the target similarity of each template image block and a target MR image block in the target MR image;
determining the weight of each template image block according to the target similarity;
and calculating and determining the label value of the target MR image according to the weight of each template image block and the label value of each template image block to obtain a segmentation result of the target MR image.
7. A knee joint cartilage dividing apparatus, comprising:
the first acquisition module is used for acquiring a target magnetic resonance MR image of the knee joint of the user and a corresponding target computed tomography CT image; wherein, the target CT image has a corresponding first hard bone tag;
a first determination module for determining a second hard bone tag of the target MR image based on a target deformation field between the first hard bone tag, the target CT image, and the target MR image;
the second acquisition module is used for acquiring target spectrums matched with the target MR image from a plurality of candidate spectrums in a preset spectrum library;
a second determining module for determining a segmented region of interest of the target MR image based on processing the second hard bone tag and a cartilage tag of the target atlas;
a third acquisition module, configured to acquire a plurality of template image blocks in the segmented region of interest;
and a third determining module, configured to determine a tag value of the target MR image according to the tag value of each template image block.
8. The knee joint cartilage segmentation device of claim 7 wherein the first determination module is specifically configured to:
performing rigid registration based on the target CT image and the target MR image to determine the target deformation field;
and calculating based on the target deformation field and the first hard bone tag to obtain the second hard bone tag.
9. An electronic device, the electronic device comprising:
a processor;
a memory for storing the processor-executable instructions;
the processor is configured to read the executable instructions from the memory and execute the instructions to implement the knee cartilage segmentation method according to any one of claims 1-6.
10. A computer-readable storage medium, characterized in that the storage medium stores a computer program for executing the knee joint cartilage segmentation method according to any one of the preceding claims 1-6.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310176233.6A CN116245839B (en) | 2023-02-24 | 2023-02-24 | Knee joint cartilage segmentation method, device, equipment and medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310176233.6A CN116245839B (en) | 2023-02-24 | 2023-02-24 | Knee joint cartilage segmentation method, device, equipment and medium |
Publications (2)
Publication Number | Publication Date |
---|---|
CN116245839A true CN116245839A (en) | 2023-06-09 |
CN116245839B CN116245839B (en) | 2023-09-29 |
Family
ID=86632771
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202310176233.6A Active CN116245839B (en) | 2023-02-24 | 2023-02-24 | Knee joint cartilage segmentation method, device, equipment and medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN116245839B (en) |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102614036A (en) * | 2012-04-24 | 2012-08-01 | 北京纳通科技集团有限公司 | Knee joint prosthesis pad, shinbone base element and knee joint prosthesis |
US20190350658A1 (en) * | 2016-07-05 | 2019-11-21 | 7D Surgical Inc. | Systems and methods for performing intraoperative image registration |
CN112826590A (en) * | 2021-02-02 | 2021-05-25 | 复旦大学 | Knee joint replacement spatial registration system based on multi-modal fusion and point cloud registration |
CN113558766A (en) * | 2021-07-19 | 2021-10-29 | 北京纳通医学研究院有限公司 | Image registration method and device, surgical robot and surgical robot system |
US20220012890A1 (en) * | 2020-07-01 | 2022-01-13 | University Of Iowa Research Foundation | Model-Based Deep Learning for Globally Optimal Surface Segmentation |
US20220183845A1 (en) * | 2009-02-25 | 2022-06-16 | Zimer, Inc. | Method of generating a patient-specific bone shell |
CN114723762A (en) * | 2022-04-22 | 2022-07-08 | 瓴域影诺(北京)科技有限公司 | Automatic knee joint CT image segmentation method and device and electronic equipment |
CN115546095A (en) * | 2022-01-28 | 2022-12-30 | 北京歌锐科技有限公司 | Image registration method and registration device |
-
2023
- 2023-02-24 CN CN202310176233.6A patent/CN116245839B/en active Active
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20220183845A1 (en) * | 2009-02-25 | 2022-06-16 | Zimer, Inc. | Method of generating a patient-specific bone shell |
CN102614036A (en) * | 2012-04-24 | 2012-08-01 | 北京纳通科技集团有限公司 | Knee joint prosthesis pad, shinbone base element and knee joint prosthesis |
US20190350658A1 (en) * | 2016-07-05 | 2019-11-21 | 7D Surgical Inc. | Systems and methods for performing intraoperative image registration |
US20220012890A1 (en) * | 2020-07-01 | 2022-01-13 | University Of Iowa Research Foundation | Model-Based Deep Learning for Globally Optimal Surface Segmentation |
CN112826590A (en) * | 2021-02-02 | 2021-05-25 | 复旦大学 | Knee joint replacement spatial registration system based on multi-modal fusion and point cloud registration |
CN113558766A (en) * | 2021-07-19 | 2021-10-29 | 北京纳通医学研究院有限公司 | Image registration method and device, surgical robot and surgical robot system |
CN115546095A (en) * | 2022-01-28 | 2022-12-30 | 北京歌锐科技有限公司 | Image registration method and registration device |
CN114723762A (en) * | 2022-04-22 | 2022-07-08 | 瓴域影诺(北京)科技有限公司 | Automatic knee joint CT image segmentation method and device and electronic equipment |
Non-Patent Citations (5)
Title |
---|
ANDRE MASTMEYER等: "Patch-based Label Fusion using Local Confidence-Measure and Weak Segmentations", 《PROCEEDINGS OF SPIE-THE INTERNATIONAL SOCIETY FOR OPTICAL ENGINEERING》, pages 1 - 13 * |
LIANG SAN等: "Automatic atlas-based three-label cartilage segmentation from MR knee images", 《2012 IEEE WORKSHOP ON MATHEMATICAL METHODS IN BIOMEDICAL IMAGE ANALYSIS》, pages 1 - 6 * |
TABRIZI, PR等: "Acetabular cartilage segmentation in CT arthrography based on a bone-normalized probabilistic atlas", 《INTERNATIONAL JOURNAL OF COMPUTER ASSISTED RADIOLOGY AND SURGERY》, pages 433 - 446 * |
ZARYCHATA PIOTR: "Atlas-Based Segmentation in Extraction of Knee Joint Bone Structures from CT AND MR", 《SENSORS》, pages 1 - 21 * |
姬东岑: "医学图像配准算法的研究", 《中国优秀硕士学位论文全文数据库 医药卫生科技辑》, pages 060 - 41 * |
Also Published As
Publication number | Publication date |
---|---|
CN116245839B (en) | 2023-09-29 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
TWI755853B (en) | Mage processing method, electronic device and computer-readable storage medium | |
JP2022502739A (en) | Image processing methods and devices, electronic devices and storage media | |
CN111292420B (en) | Method and device for constructing map | |
CN111260774B (en) | Method and device for generating 3D joint point regression model | |
CN110930438B (en) | Image registration method, device, electronic equipment and storage medium | |
CN108778134B (en) | System and method for characterizing the central axis of a bone from a 3D anatomical image | |
CN111598902B (en) | Image segmentation method, device, electronic equipment and computer readable medium | |
CN113689372B (en) | Image processing method, apparatus, storage medium, and program product | |
CN113469295B (en) | Training method for generating model, polyp recognition method, device, medium, and apparatus | |
CN113487608A (en) | Endoscope image detection method, endoscope image detection device, storage medium, and electronic apparatus | |
CN113496512B (en) | Tissue cavity positioning method, device, medium and equipment for endoscope | |
CN113994371B (en) | Method and apparatus for image analysis | |
CN113706562B (en) | Image segmentation method, device and system and cell segmentation method | |
CN112330788A (en) | Image processing method, image processing device, readable medium and electronic equipment | |
CN113610034B (en) | Method and device for identifying character entities in video, storage medium and electronic equipment | |
CN117152442B (en) | Automatic image target area sketching method and device, electronic equipment and readable storage medium | |
CN114332033A (en) | Endoscope image processing method, apparatus, medium, and device based on artificial intelligence | |
CN111915532B (en) | Image tracking method and device, electronic equipment and computer readable medium | |
CN116245839B (en) | Knee joint cartilage segmentation method, device, equipment and medium | |
CN117078714A (en) | Image segmentation model training method, device, equipment and storage medium | |
CN112750124B (en) | Model generation method, image segmentation method, model generation device, image segmentation device, electronic equipment and storage medium | |
CN111598025B (en) | Training method and device for image recognition model | |
CN111968030B (en) | Information generation method, apparatus, electronic device and computer readable medium | |
CN111292365A (en) | Method, device, electronic equipment and computer readable medium for generating depth map | |
Anas et al. | A statistical shape+ pose model for segmentation of wrist CT images |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |